[HN Gopher] WeatherNext 2: Our most advanced weather forecasting...
       ___________________________________________________________________
        
       WeatherNext 2: Our most advanced weather forecasting model
        
       Author : meetpateltech
       Score  : 172 points
       Date   : 2025-11-17 15:04 UTC (7 hours ago)
        
 (HTM) web link (blog.google)
 (TXT) w3m dump (blog.google)
        
       | xd1936 wrote:
       | Pricing, I think?
       | 
       | https://developers.google.com/maps/billing-and-pricing/prici...
        
       | LogicFailsMe wrote:
       | This year, the wild variance in hourly weather reports on my
       | phone has really been something. I attributed it to likely budget
       | cuts as a result of DOGE, but if those forecasts came from Google
       | itself the whole time, all is clear now.
        
         | politelemon wrote:
         | I find that unlikely, my forecasts for much of Europe and East
         | Asia have been consistently accurate.
        
           | dylan604 wrote:
           | How do DOGE implemented budget cuts affect European or East
           | Asian forecasts? Those are not the forecasts that someone
           | suspecting departmental DOGEing to be a fault.
        
             | NoiseBert69 wrote:
             | If the US does less data gathering (balloon starts, buoy
             | maintenance, setting up weather huts in super remote sites,
             | etc.) it will affect all forecasts.
             | 
             | Models all use a "current world state" of all sensors
             | available to bootstrap their runs.
             | 
             | Similar thing happened during the beginning of Covid-19:
             | they are using modified cargo/passenger planes to gather
             | weather data during their routine trips. Suddenly this huge
             | data source was gone (but was partially replaced by the
             | experimental ADM-Aeolus satellite - which turned out to be
             | a huge global gamer changer due to its unexpected high
             | quality data)
        
             | integralid wrote:
             | But GP said they only USED TO blame DOGE, and blame Google
             | now?
        
           | LogicFailsMe wrote:
           | Yeah... So you know that's not the United States right?
           | Though judging by the down votes, it's quite triggering for
           | some and I can't say which side when I pivot from blaming
           | DOGE to blaming bad AI. Curious(tm)...
           | 
           | And I say that as a huge fan of AI, but being vocally self-
           | critical is an important attribute for professional success
           | in AI and elsewhere.
        
       | binsquare wrote:
       | I find it interesting that they quantify the improvement on speed
       | and number of forecast-ed scenarios but lack details on how it
       | results in improved accuracy of the forecast per:
       | 
       | ``` WeatherNext 2 can generate forecasts 8x faster and with
       | resolution up to 1-hour. This breakthrough is enabled by a new
       | model that can provide hundreds of possible scenarios. ```
       | 
       | As an end user, all I care is that there's one accurate
       | forecasted scenario.
        
         | NoiseBert69 wrote:
         | As a end user I also want to see the variance to get a feeling
         | of the uncertainty.
         | 
         | Quite a lot of weather sites offer this data in an easily
         | eatable visual format.
        
         | Sanzig wrote:
         | Indeed. The most important benchmark is accuracy and how well
         | it stacks up against existing physics-based models like GFS or
         | ECMWF.
         | 
         | Sure, those big physics-based models are very computationally
         | intensive (national weather bureaus run them on sizeable HPC
         | clusters), but you only need to run them every few hours in a
         | central location and then distribute the outputs online. It's
         | not like every forecaster in a country needs to run a model,
         | they just need online access to the outputs. Even if they
         | _could_ run the models themselves, they would still need the
         | mountains of raw observation data that feeds the models
         | (weather stations, satellite imagery, radars, wind
         | profilers...). And these are usually distributed by... the
         | national weather bureau of that country. So the weather bureau
         | might as well do the number crunching as well and distribute
         | that.
        
         | agildehaus wrote:
         | They integrated "MetNet-3" into Google products and my personal
         | perception was accuracy decreased.
        
         | tylervigen wrote:
         | For lay-users they could have explained that better. I think
         | they may not have completely uninformed users in mind for this
         | page though.
         | 
         | Developing an ensemble of possible scenarios has been the
         | central insight of weather forecasting since the 1960s when
         | Edward Lorenz discovered that tiny differences in initial
         | conditions can grow exponentially (the "butterfly effect").
         | Since they could really do it in the 90s, all competitive
         | forecasts are based on these ensemble models.
         | 
         | When you hear "a 70% chance of rain," it more or less means
         | "there was rain in 70 of the 100 scenarios we ran."[0] There is
         | no "single accurate forecast scenario."
         | 
         | [0] Acknowledging this dramatically oversimplifies the models
         | and the location where the rain could occur.
        
           | sweettea wrote:
           | My understanding is that it's an expected value based on
           | coverage in each of the ensemble scenarios, not quite as
           | simplified as "how many scenarios was there rain in this
           | forecast cell".
           | 
           | At least for the US NWS: if 30 of 100 scenarios result in 50%
           | shower coverage, and 70 out of 100 result in 0%, this is
           | reported as 15% chance of rain. Which is exactly the same as
           | 15 with 100% coverage and 85 with 0% coverage, or 100 with
           | 15% coverage.
           | 
           | Understanding this, and digging further into the forecast,
           | gives a better sense of whether you're likely to encounter
           | widespread rainfall or spotty rainfall in your local area.
        
         | meandthewallaby wrote:
         | This is really important: You're not the end user of this
         | product. These types of models are not built for laypeople to
         | access them. You're an end user of a product that may use and
         | process this data, but the CRPS scorecard, for example, should
         | mean nothing to you. This is specifically addressing an under-
         | dispersion problem in traditional ensemble models, due to a
         | limited number (~50) and limited set of perturbed initial
         | conditions (and the fact that those perturbations do very
         | poorly at capturing true uncertainty).
         | 
         | Again, you, as an end user, don't need to know any of that. The
         | CRPS scorecard is a very specific measure of error. I don't
         | expect them to reveal the technical details of the model, but
         | an industry expert instantly knows what WeatherBench[1] is, the
         | code it runs, the data it uses, and how that CRPS scorecard was
         | generated.
         | 
         | By having better dispersed ensemble forecasts, we can more
         | quickly address observation gaps that may be needed to better
         | solidify certain patterns or outcomes, which will lead to more
         | accurate deterministic forecasts (aka the ones you get on your
         | phone). These are a piece of the puzzle, though, and not one
         | that you will ever actually encounter as a layperson.
         | 
         | [1]: https://sites.research.google/gr/weatherbench/
        
           | counters wrote:
           | > By having better dispersed ensemble forecasts, we can more
           | quickly address observation gaps that may be needed to better
           | solidify certain patterns or outcomes, which will lead to
           | more accurate deterministic forecasts.
           | 
           | Sorry - not sure this is a reasonable take-away. The models
           | here are all still initialized from analysis performed by
           | ECMWF; Google is not running an in-house data assimilation
           | product for this. So there's no feedback mechanism between
           | ensemble spread/uncertainty and the observation itself in
           | this stack. The output of this system could be interrogated
           | using something like Ensemble Sensitivity Analysis, but
           | there's nothing novel about that and we can do that with
           | existing ensemble forecast systems.
        
           | DoctorOetker wrote:
           | Sorry to hijack you: I have some questions regarding current
           | weather models:
           | 
           | I am personally _not_ interested in predicting the weather as
           | end users expect it, rather I am interested in representative
           | evolutions of wind patterns. I.e. specify some location (say
           | somewhere in the North Sea, or perhaps on mainland Western
           | Europe), and a date (say Nov 12) without specifying a year,
           | and would like to have the wind patterns at different heights
           | for that location say for half an hour. Basically running
           | with different seeds, I want to have representative
           | evolutions of the wind vector field (without specifying
           | starting conditions, other than location and date, i.e. NO
           | prior weather).
           | 
           | Are there any ML models capable of delivering realistic and
           | representative wind gust models?
           | 
           | (The context is structural stability analysis of hypothetical
           | megastructures)
        
         | sails wrote:
         | As others have explained, ensembles are useful.
         | 
         | As a layperson, what _is_ useful is to look at the difference
         | between models. My long range favourite is to compare ECMWF and
         | GFS27 and if the deviation is high (windy app has this) then
         | you can bet that at least one of them is likely wrong
        
       | jakewins wrote:
       | Is anyone aware of good sources of higher resolution models?
       | Hourly resolution like this model provides doesn't help much now
       | that energy markets have moved to 15-min and 5-min resolution.
        
         | vaughnegut wrote:
         | Windy allows you to select your model. For that reason it's my
         | go to for accuracy.
         | 
         | Different models have different strengths, though. Some are
         | shorter range (72h) or longer range (1-3 weeks). Some are
         | higher resolution for where you live (the size of an area which
         | it assigns a forecast to, so your forecast is more local).
         | 
         | Some governments will have their own weather model for your
         | country that is the most accurate for where you live. What I
         | did for a long time was use Windy and use HDRPS (a Canadian
         | short range model with a higher resolution in Canada so I have
         | more accurate forecasts). Now I just use the government of
         | Canada weather app.
         | 
         | I genuinely wonder what the weather Channel, iPhone/Android
         | official weather apps, etc. use under the hood for global
         | models. My gut says ECMWF (a European model with global
         | coverage) mixed with a little magic.
        
           | chneu wrote:
           | Windy or Ventusky. Both really solid.
        
         | mlmonkey wrote:
         | How does one use weather data in an energy market, if you don't
         | mind my asking?
        
           | bitdivision wrote:
           | Seems like it would be pretty useful to forecast the supply
           | of renewables (wind, solar, maybe some hydro).
        
             | edbaskerville wrote:
             | Indeed. In the not-too-distant future where renewables are
             | the vast majority of generation (sooner in China than in
             | the U.S. at current rates of progress), the weather matters
             | more and more.
        
           | hackitup7 wrote:
           | Temperature and weather can have a huge impact on power
           | prices. Small examples:
           | 
           | * 90 degree day => more air conditioning usage => power goes
           | up
           | 
           | * 70 degree sunny day => that's also July 4th (holiday, not a
           | work day when factories or heavy industry are running) =>
           | lots of people go outside + it's a holiday => power
           | consumption goes DOWN
           | 
           | * 10 degree difference colder/hotter => impacts resistance of
           | power lines => impacts transmission congestion credits =>
           | impacts power prices
           | 
           | It's a fascinating industry. One power trading company that I
           | consulted for had a meteorologist who was also a trader. They
           | literally hired the dude from a news channel if I remember it
           | correctly.
        
           | jakewins wrote:
           | Yeah exactly like hackitup7 says, it has a huge impact on
           | both sides of the supply and demand equation. It both drives
           | house heating and cooling, which has a massive consumption
           | impact, and it drives solar and wind production.
           | 
           | But knowing "there will be a massive drop in temperature
           | between 1pm->2pm" doesn't help much anymore, you need to know
           | which 15-minute or 5-minute block all those heat pumps will
           | kick on in, to align with markets moving to 15-min and 5-min
           | contracts.
           | 
           | Major forecasts like ECMWF don't have anything like that
           | resolution; they model the planet at 3 hour time scale, with
           | a 1 hour "reanalysis" model called ERA5.. hoping to find good
           | info on what's available at higher resolution.
        
         | trillic wrote:
         | HRRR is 15 min res updated hourly. It's not that resolution all
         | the way out only 18 hours I think.
        
       | timenotwasted wrote:
       | It feels like real weather
       | AI|Forecast|whatever_you_want_to_call_it is still far, far away.
       | Maybe it's just the consumer aspect of weather apps but I don't
       | feel as if I get any more accurate data now than I did back when
       | my parents turned to the daily weather channel for the forecast.
       | Still a lot of clear days when rain was predicted or the even
       | more dreaded torrential downpour when it was supposed to be sunny
       | and clear.
       | 
       | Obviously all I have is anecdata for what I'm mentioning here but
       | from a consumer perspective I don't feel like these model
       | enhancements are really making average folks feel as if weather
       | is any more understood than it was decades ago.
        
         | jstummbillig wrote:
         | No need for anecdata! We have the data:
         | https://ourworldindata.org/weather-forecasts
         | 
         | tdlr: Weather forecasts have improved a lot
        
           | timenotwasted wrote:
           | That's actually really helpful to understand better, thank
           | you!
        
           | baron816 wrote:
           | I remember when it was a trope that the weatherman was always
           | wrong and that the weather was the prototypal thing that was
           | inherently "unpredictable".
        
         | deanputney wrote:
         | I've found this to be more related to poor representation of
         | the data than inaccurate data.
         | 
         | For example on Apple's Weather app, a "rainy" day means a high
         | chance of rain at any point during the day. If it's 80% chance
         | of rain at 5am and sunny the rest of the day- that counts as
         | rainy. You can see an hourly report for more info, and
         | generally this is pretty accurate. You have to learn how to
         | find the right data, know your local area, and interpret it
         | yourself.
         | 
         | Then you have to consider what effects this has on your plans
         | and it gets more complicated. Finding a window to walk the dog,
         | choosing a day to go sailing, or determining conditions for
         | backcountry skiing all have different requirements and
         | resources. What I'd like AI to do is know my own interests and
         | highlight what the forecast means for me.
        
           | semi-extrinsic wrote:
           | In Norway people are extremely weather-focused, and the
           | national weather service delivers quite advanced graphics for
           | people to understand what is going on.
           | 
           | The standard graph that most people look at to get an idea
           | about today and tomorrow: https://www.yr.no/en/forecast/graph
           | /1-72837/Norway/Oslo/Oslo...
           | 
           | The live weather radar which shows where it is raining right
           | now and prediction/history for rain +/- 90 minutes. This is
           | accurate enough that you can use it to time your walk from
           | the office to the subway and avoid getting wet:
           | https://www.yr.no/en/map/radar/1-72837/Norway/Oslo/Oslo/Oslo
           | 
           | Then you have more specialised forecasts of course. Dew
           | point, feels like temperature, UV, pollution, avalanche
           | risks, statistics, sea conditions, tides, ... People tend to
           | geek out quite heavily on these.
        
             | Alexsky2 wrote:
             | The United States (National Weather Service) has these too:
             | https://www.weather.gov/forecastmaps/
             | 
             | I use these and Windy: https://www.windy.com/
             | 
             | In my experience, these forecasts are really good 5-7 days
             | out, and then degrade in reliability (as you would expect
             | from predictions of chaotic systems). The apps that show
             | you a rain cloud and a percentage number are always
             | terrible in my experience for some reason, even if the
             | origin of the data is the same. I'm not sure why that might
             | be.
        
         | tylervigen wrote:
         | > I don't feel as if I get any more accurate data now than I
         | did back when my parents turned to the daily weather channel
         | for the forecast.
         | 
         | The accuracy improvement is provable. A four-day forecast today
         | is as accurate as a one-day forecast 30 years ago. And this is
         | supremely impressive, because the difficulty of predicting the
         | weather grows exponentially, not linearly, with time.
         | 
         | You are welcome to your feelings - and to be fair, I'm not sure
         | that our understanding of the weather has improved as much as
         | our computational power to extend predictions has.
        
           | counters wrote:
           | You're 100% correct, but there's a subtlety in what the
           | commenter is talking about.
           | 
           | Yes, _in aggregate_, forecasts are objectively, quantifiably
           | better in 2025 than they were in 2005 let alone 1985. But any
           | given, specific forecast may have unique and egregious
           | failure modes. Look no further than the GFS' complete
           | inability to lock on to the forecast track for Hurricane
           | Melissa a month ago. This is dramatically compounded when you
           | look at mesoscale forecast, where higher spatial resolution
           | is a liability that leads to double-penalty errors (e.g.
           | setting up a mesoscale snow squall band just slightly south
           | of where it actually develops).
           | 
           | And keep in mind that the benchmarks shared from this model
           | product are evaluating an ensemble mean, which further
           | confounds things. Even if the ensemble mean is well-
           | calibrated and accurate, there can be critical spread from
           | the ensemble members themselves.
        
         | lysecret wrote:
         | The thing is that regular weather forecasts are also not that
         | great.
        
       | atonse wrote:
       | Anyone know whether we can use this to simulate hurricanes/floods
       | in particular areas, instead of looking at real existing data and
       | helping model an existing hurricane as it's happening? (which is
       | definitely more important and impactful, but the simulation angle
       | is the one I happen to be curious about at the moment).
       | 
       | Like if I wanted to simulate whether something like Hurricane
       | Melissa would've gone through a handful of southern US states,
       | what would the effect have been, from an insurance or resiliency
       | standpoint.
        
         | counters wrote:
         | That's not really what a weather model "does."
        
       | cryptoz wrote:
       | 15 years later and still no word from Google if they will use the
       | barometers in Android devices to assimilate surface pressure
       | data. It has been shown that this can improve forecast accuracy.
       | I think IBM may be doing it with their weather apps, but
       | Google/Apple would have dramatically more data available.
       | 
       | Apple even bought Dark Sky, which purported to do this but never
       | released any information - so I doubt they really did do it. And
       | if they did, I doubt Apple continued the practice.
       | 
       | Been waiting a long time to hear Google announce they'll use your
       | barometer to give you a better forecast. Still waiting I guess.
        
         | Majromax wrote:
         | > 15 years later and still no word from Google if they will use
         | the barometers in Android devices to assimilate surface
         | pressure data.
         | 
         | For WeatherNext, the answer is 'no'. The paper
         | (https://arxiv.org/abs/2506.10772) describes in detail what
         | data the model uses, and direct assimilation of user barometric
         | data is not on the list.
        
         | counters wrote:
         | The community has mostly abandoned SPO data. It's
         | extraordinarily difficult to use this data because of social
         | issues like PII and technical ones like QA/QC. But even more
         | importantly, there's very little compelling evidence that the
         | data makes much of any difference whatsoever in real forecasts.
        
       | AceJohnny2 wrote:
       | Is this the same model as provided the most accurate hurricane
       | predictions this season?
       | 
       | https://arstechnica.com/science/2025/11/googles-new-weather-...
        
       | lysecret wrote:
       | Im pretty deep into this topic and what might be interesting to
       | an outsider is that the leading models like neuralgcm/weathernext
       | 1 before as well as this model now are all trained with a "crps"
       | objective which I haven't seen at all outside of ml weather
       | prediction.
       | 
       | Essentially you add random noise to the inputs and train by
       | minimizing the regular loss (like l1) and at the same time
       | maximizing the difference between 2 members with different random
       | noise initialisations. I wonder if this will be applied to more
       | traditional genai at some point.
        
         | rytill wrote:
         | What is the goal of doing that vs using L2 loss?
        
           | lysecret wrote:
           | To encourage diversity between the different members in an
           | ensemble. I think people are doing very similar things for
           | MOE networks but im not that deep into that topic.
        
           | sunshinesnacks wrote:
           | The goal of using CRPS is to produce an ensemble that is a
           | good probabilistic forecast without needing calibration/post
           | processing.
           | 
           | [edit: "without", not "with"]
        
         | cleak wrote:
         | That's pretty neat. It reminds me of how VAEs work:
         | https://en.wikipedia.org/wiki/Variational_autoencoder
        
         | nerdponx wrote:
         | > Essentially you add random noise to the inputs and train by
         | minimizing the regular loss (like l1) and at the same time
         | maximizing the difference between 2 members with different
         | random noise initialisations. I wonder if this will be applied
         | to more traditional genai at some point.
         | 
         | We recently had a situation where we specifically wanted to
         | generate 2 "different" outputs from an optimization task and
         | struggled to come up with a good heuristic for doing so. Not at
         | all a GenAI task, but this technique probably would have helped
         | us.
        
       | bilsbie wrote:
       | Where can I use this? I've been trying to find hyperlocal
       | forecasts like darksky used to be.
        
         | paxys wrote:
         | > We're now taking our research out of the lab and putting it
         | into the hands of users. WeatherNext 2's forecast data is now
         | available in Earth Engine and BigQuery. We're also launching an
         | early access program on Google Cloud's Vertex AI platform for
         | custom model inference.
         | 
         | > By incorporating WeatherNext technology, we've now upgraded
         | weather forecasts in Search, Gemini, Pixel Weather and Google
         | Maps Platform's Weather API. In the coming weeks, it will also
         | help power weather information in Google Maps.
        
           | jadbox wrote:
           | Google Maps has... weather predictions?
        
             | batrat wrote:
             | if you search for a city usually it shows the current
             | weather, but I've seen in some cities there is also a 7 day
             | forecast
        
             | abdullahkhalids wrote:
             | If you want to accurately predict times for future trips,
             | you need weather predictions.
        
         | jachee wrote:
         | Apple integrated the hyperlocal darksky stuff into their native
         | Weather app. It had a few growing pains, but it's as good as it
         | ever was, imho.
        
           | baxtr wrote:
           | Agreed.
           | 
           | The one thing I'd like them to improve are the precipitation
           | maps though. They just feel awkward and unreliable.
        
         | trillic wrote:
         | The HRRR is VERY good in my opinion. It updates hourly with a
         | 15-minute resolution 18 hours out and hourly 48 hours out.
         | 
         | https://rapidrefresh.noaa.gov/hrrr/
        
         | ellisv wrote:
         | Precip.ai or go grab the MRMS data yourself
        
         | SoftTalker wrote:
         | Look out the window? Works as well as anything else for me.
        
         | driverdan wrote:
         | They link to the API: https://mapsplatform.google.com/maps-
         | products/weather/
        
         | carabiner wrote:
         | I never understood the acclaim for dark sky. It never seemed
         | very accurate, and the forecasts changed so rapidly that they
         | weren't of much use. "Rain for next 2 hours" would become
         | "Intermittent rain for the next 30 minutes" 10 minutes later.
        
         | plantain wrote:
         | Darksky was only ever good marketing.
        
           | carabiner wrote:
           | The UX was great but predictions were terrible. I swear the
           | only people who liked it did so out of confirmation bias,
           | which can affect anyone. Just a week ago here on HN, there
           | were users here claiming Farmer's Almanac was accurate.
        
       | lampiaio wrote:
       | Reminds me of a funny WWII story:
       | 
       | Kenneth Arrow and his statisticians found that their long-range
       | forecasts were no better than numbers pulled out of a hat. The
       | forecasters agreed and asked their superiors to be relieved of
       | this duty. The reply was: "The Commanding General is well aware
       | that the forecasts are no good. However he needs them for
       | planning purposes."
        
         | empath75 wrote:
         | There is a fairly compelling argument that divination in the
         | ancient world was not a useless waste of time, as is commonly
         | assumed, but that having either a process or a person that can
         | make essentially random choices for them allowed people to make
         | hard, consequential decisions where they might otherwise be
         | paralyzed, especially when the penalty for not acting was worse
         | than making a mistake.
        
           | twoodfin wrote:
           | Fascinating. I suppose it also encourages developing
           | adaptable strategies that accommodate imperfect information,
           | vs. succumbing to wishful thinking or other forms of
           | cognitive bias.
        
           | OisinMoran wrote:
           | I've also read that a source of randomness like that could
           | help prevent things like over-extracting some land
        
       | bigtones wrote:
       | Googles weather prediction engine is already very good, and the
       | new hurricane model was breathtakingly good this season when
       | tested against actual hurricane paths. Meanwhile, the US
       | Government Global Forecasting System continues to get worse.
       | 
       | https://arstechnica.com/science/2025/11/googles-new-weather-...
        
       ___________________________________________________________________
       (page generated 2025-11-17 23:00 UTC)